agentsclimarketplace
Sign in

Shelves Research & analysis

Papers & literature

619 rows from 235 repositories

Academic sources, and reading them at volume.

What Papers & literature skills agree on

202 skill files read, by 185 of the 191 authors on this shelf whose files we hold, 2026-09-06

The middle one of the 31 measured here is ~2.2k tokens long, counted with cl100k_base

Counted by distinct author, so one author publishing three of these counts once. Where a claim sits in fewer files than authors, that is said: a claim held by forty authors across three files is one file people copied, not forty people who agreed. Near-identical wordings are grouped and the other wordings are shown, so the grouping is yours to check.

What they tell the agent to do

  1. Screen sources by title, abstract, then full text16 of 185 in 9 filesalso worded as Screen titles, then abstracts, then full texts; Screen title, abstract, then full text
  2. Create a search protocol before collecting sources11 of 185 in 5 filesalso worded as Create search protocol before collecting sources
  3. Convert the prompt into a searchable research question11 of 185 in 5 filesalso worded as Convert prompt into searchable research question
  4. Keep a reproducible search log11 of 185 in 5 filesalso worded as Record reproducible search log; Keep a search log that makes review reproducible
  5. Group evidence by theme, not per paper11 of 185 in 5 filesalso worded as Group evidence thematically, not paper by paper; Group evidence by theme, not by paper
  6. Ask the user which review rigor level is needed11 of 185 in 5 filesalso worded as Ask the user which rigor level is needed; Ask the user which review rigor is needed
  7. Use a structured extraction table11 of 185 in 5 filesalso worded as Extract data into a structured table; Extract data into structured table
  8. Separate claims by confidence level10 of 185 in 4 filesalso worded as Separate claims into confidence levels
  9. Deduplicate by DOI, identifier, then title10 of 185 in 4 filesalso worded as Deduplicate by DOI, ID, then title; Deduplicate by DOI, then ID, then title
  10. Record exclusion reasons at each screening stage9 of 185 in 3 filesalso worded as Record exclusion reasons during screening
  11. Verify citation identifiers before finalizing9 of 185 in 4 filesalso worded as Verify all citations before final submission; Verify citations before finalizing
  12. Search a minimum of three databases7 of 185 in 6 filesalso worded as Search at least three complementary databases; Search at least three databases and document search strings
  13. Cite every claim or support it with data7 of 185also worded as Cite every claim with a source; Support every claim with data, literature, or cases
  14. Save raw source metadata separately from prose6 of 185 in 2 filesalso worded as Save raw source data separately from final prose
  15. Include an AI disclosure statement in every paper6 of 185 in 5 filesalso worded as Include AI disclosure statement in reports; Include AI usage disclosure statement in every paper

What they tell it not to do

  1. Do not cite a paper for claims it does not make.14 of 185 in 8 filesalso worded as Do not cite a paper for a claim it does not make; Do not cite papers for claims they do not make
  2. Do not treat search snippets as evidence.12 of 185 in 6 filesalso worded as Do not use search snippets as scientific evidence; Never treat search snippets as evidence
  3. Never fabricate citations.12 of 185also worded as Do not fabricate citations; Never fabricate data or citations
  4. Do not omit negative or conflicting findings11 of 185 in 5 filesalso worded as Never omit negative or conflicting findings
  5. Do not claim systematic-review rigor without a reproducible protocol11 of 185 in 5 filesalso worded as Do not claim systematic rigor without reproducible protocol; Do not claim systematic rigor without a reproducible protocol
  6. Do not use a single database for broad claims11 of 185 in 5 filesalso worded as Do not use a single database for broad claims; Never use a single database for broad claims
  7. Do not mix unlabeled preprints, reviews, and primary studies10 of 185 in 4 filesalso worded as Do not mix preprints, reviews, and primary studies unlabeled
  8. Do not cite studies without verifiable records6 of 185 in 5 filesalso worded as Do not cite studies without verifiable records; Never submit unverified citations
  9. No personal attacks or dismissive language5 of 185 in 4 filesalso worded as Do not use personal attacks or demeaning language; No personal attacks or demeaning language
  10. Do not summarize studies one by one5 of 185also worded as do not summarize papers one by one; Never write study-by-study summaries

What they expect to be installed

  1. arXiv27 of 185 in 20 files
  2. Crossref23 of 185 in 15 files
  3. Semantic Scholar23 of 185 in 16 files
  4. PubMed19 of 185 in 12 files
  5. curl17 of 185 in 16 files
  6. python316 of 185
  7. pandoc13 of 185
  8. Semantic Scholar API12 of 185 in 11 files
  9. xelatex12 of 185 in 11 files
  10. uv12 of 185

What they ask it to produce

  1. Search log table10 of 185 in 4 filesalso worded as Search log
  2. Literature review document with references10 of 185 in 4 filesalso worded as Literature review document
  3. Citation audit report10 of 185 in 8 filesalso worded as Citation verification report; Citation audit or error report
  4. Markdown literature review document10 of 185 in 9 filesalso worded as markdown literature review in workspace; Markdown review file
  5. Revision roadmap9 of 185also worded as Review reports and Revision Roadmap; Prioritized Revision Roadmap
  6. PRISMA flow diagram8 of 185 in 7 filesalso worded as PRISMA 2020 flow diagram
  7. Paper configuration record6 of 185 in 5 files
  8. Bilingual abstract with keywords6 of 185 in 5 files

When Papers & literature authors say to reach for one

The situations these authors wrote into their own files, counted out of the same 185 authors, with the skills that name each one

How Papers & literature skills are built

591 skill directories by 213 authors, read from their repositories’ own file trees 2026-08-05

The middle bundle among those shipping files is 5 files, 28.8 KB beside SKILL.md

Counted by distinct author, same as above, so one author publishing forty template copies counts once. SKILL.md itself is not counted as a file, so a single-file skill is one where that file is the whole skill.

The shape

  1. SKILL.md is the whole skill62 of 213 authors, 199 of 591 skills
  2. files ship beside it151 of 213 authors, 392 of 591 skills
  3. executable scripts ship inside92 of 213 authors, 212 of 591 skills

The folders they converge on

  1. references/91 of 213 authors, 253 of 591 skills
  2. scripts/81 of 213 authors, 192 of 591 skills
  3. agents/40 of 213 authors, 86 of 591 skills
  4. assets/31 of 213 authors, 51 of 591 skills
  5. examples/24 of 213 authors, 63 of 591 skills
  6. templates/21 of 213 authors, 45 of 591 skills

  • Academic paper reviewer

    zebbern/claude-code-guide/skills/academic-paper-reviewer Skill

    4,568★ repo

    Claude Code Guide - Setup, Commands, workflows, agents, skills & tips-n-tricks go from beginner to power user!

  • Arxiv mcp server

    blazickjp/arxiv-mcp-server/io.github.blazickjp/arxiv-mcp-server MCP server

    3,047★ repo

    Search arXiv papers, download full text, semantic search, citation graphs, and alerts via MCP.

  • Econ write

    hanlulong/econ-writing-skill/skills/econ-write Skill

    529★ repo

    Agent Skill that transforms AI assistants into expert economics paper writers. Synthesizes 50+ guides by Cochrane, McCloskey, Shapiro, Head, Bellemare, Goldin, Kremer. Compatible with Claude Code and OpenAI Codex.

  • Light citation

    Light0305/Light-skills/skills/light-citation Skill

    521★ repo

    An AI workflow skill pack for research, competitions, and innovation projects.

  • Humanities writing companion

    tizzy916/humanities-writing-companion Skill

    no license357★

    End-to-end humanities writing assistant — an Agent Skill (open SKILL.md format). 11 modes from Socratic research-question sharpening through AI-use disclosure. Bilingual (EN/中文), discipline-aware (literature/history/philosophy/art/religion/linguistics + cross-disciplinary). Four-layer critique, calibratable devils advocate, voice preservation.

  • Arxiv search

    DougTrajano/pydantic-ai-skills/examples/skills/arxiv-search Skill

    357★ repo

    This package implements Agent Skills (https://agentskills.io) support with progressive disclosure for Pydantic AI. Supports filesystem and programmatic skills.

  • Xs arxiv

    karaage0703/ai-assistant-workspace/skills/xs-arxiv Skill

    136★ repo

  • Rival search mcp

    damionrashford/RivalSearchMCP/plugins/rival-search-mcp-skills/skills/rival-search-mcp Skill

    119★ repo

    Deterministic research MCP server on FastMCP 3 — 5-engine web search, 9-platform social search, 6 academic DBs, news aggregation, entity profiles, conflict detection, document analysis. No API keys. No in-server LLM. Structured outputs for agent chaining.

  • Aigc detector

    free-revalution/AIGC-Detector-Pro/.claude/skills/aigc-detector Skill

    112★ repo

    AIGC 检测论文 AI 降率工具 - Claude Code Skill for academic paper AI detection and rewriting

  • Arxiv doc builder

    ultimatile/arxiv-skills/skills/arxiv-doc-builder Skill

    41★ repo

  • Argument governance

    yha9806/academic-writing-toolkit/.claude/skills/argument-governance Skill

    27★ repo

    Local-first, evidence-controlled academic writing workflows for AI agents, with bounded revision, clean-room review, and release governance.

  • Scholar forge

    hyl-ailab/scholar-forge Skill

    27★

    Academic writing Agent Skill — citation integrity, venue intelligence, bilingual CN/EN (GB/T 7714)

  • Arxiv search

    TaewoooPark/scholar-megasearch/skills/arxiv-search Skill

    24★ repo

    Massive multi-source academic literature search for Claude Code — one skill fans out subagents across 20+ scholarly databases (arXiv, Semantic Scholar, Crossref, OpenAlex, PubMed, …), merges into a deduplicated ranked corpus, and acquires the original PDFs.

  • Write literature review

    Zsun79/LitReviewSkill/skills/write-literature-review Skill

    no license22★ repo

    LitReview Skill is an installable agent skill for end-to-end literature review generation. It helps agents conduct literature reviews with a well-designed and widely used review framework so the search process is broad, iterative, and less likely to miss relevant articles.

  • Scholar deep research

    Agents365-ai/scholar-deep-research/skills/scholar-deep-research Skill

    22★ repo

    8-phase literature-review pipeline. 7 federated sources, dedup, ranked retrieval, citation chasing, self-critique, 5 report archetypes.

  • Arxiv fetch

    yang3kc/daily_arxiv_digest/skills/arxiv-fetch Skill

    19★ repo

    Daily digest of interesting arXiv papers — an unattended LLM pipeline for cron, plus a zero-dependency agent skill your AI agent runs itself

  • Academic paper

    thtskaran/claude-skills/academic-paper Skill

    16★ repo

    Battle-tested Claude Code skills for hardening vibe-coded projects. Audit, clean, and ship AI-generated codebases with confidence.

  • Research paper review

    BESSER-PEARL/research-agent-skills/research-paper-review Skill

    16★ repo

    AI agent skills by BESSER-PEARL, systematic paper review, and more. Works with Claude Code, Cursor, Copilot, Windsurf, and any skills.sh-compatible agent

  • Thesis reviewer

    Agents365-ai/thesis-reviewer Skill

    no license9★

    Systematic thesis review skill for AI coding agents — supports all disciplines (7 modules: life sciences, medicine, CS/AI, engineering, chemistry, physics, social sciences). Master's + PhD, academic + professional degrees. 100+ checklist items, blind review risk assessment. GB/T 7713.1 aligned.

  • Arxiv

    mediause/agent-skills/arxiv Skill

    no license9★ repo

    MediaUse Skills, web operations into semantic CLI actions, AI agents can run with near-zero token cost and higher stability.

  • Bibcheck

    ericluo04/claude-academic-workflow/skills/bibcheck Skill

    no license8★ repo

    Academic research workflow for Claude Code: 14 skills (paper reading, lit review, bib auditing, preregistration, referee reports, replication packages, LaTeX, TikZ) plus a Quarto reveal.js slide system with render-time quality gates. Entirely AI-generated with Claude Code as a proof of concept.

  • Arxiv paper zh

    zeya-labs/arxiv-paper-zh/arxiv-paper-zh Skill

    7★ repo

    Source-preserving Chinese translation workflow for arXiv LaTeX papers

  • Scholar sidekick

    mlava/scholar-sidekick-mcp/plugin/skills/scholar-sidekick Skill

    7★ repo

    MCP server for Scholar Sidekick — resolve any scholarly identifier (DOI, PMID, PMCID, ISBN, arXiv, ISSN, ADS, WHO IRIS) into 10,000+ CSL styles or nine export formats, single or batch.

  • Academic paper reviewer

    yinqd3/workbuddy-skills/academic-research/academic-paper-reviewer Skill

    5★ repo

    A curated collection of WorkBuddy agent skills — academic pipeline, frontend slides, PPTX generator, tool-call repair, and more.

  • Scientific research helper

    NguyenAn2812/scientific-research-helper Skill

    5★

    Claude Skill for scientific research, thesis, and academic paper writing. Analyzes documents, provides detailed feedback, suggests structural improvements, citations, and academic language enhancement.

  • Academic paper writing skill

    xcl2005/academic-paper-writing-skill Skill

    4★

    Evidence-first Agent Skill for Codex & Claude Code: research papers, literature reviews, rebuttals, thesis writing, and academic integrity.

  • Academic paper reviewer

    tuoxie2046/claude-code-research-skills/plugins/academic-research-skills/academic-paper-reviewer Skill

    no license4★ repo

    A curated collection of Claude Code skills & plugins for academic research paper workflows — figures, writing, polishing, peer-review simulation, multi-source literature search (MCP), and full research→write→review pipelines.

  • Themis

    arsenelupin14/THEMIS/skills/themis Skill

    4★ repo

    Research workrooms for AI agents: evidence retrieval, citation audit, adversarial review, peer review gates, and clean final reports.

  • Experiment grounded paper review

    PaulClawX/research-agent/paper/experiment-grounded-paper-review Skill

    no license4★ repo

    [research-agent] Never send a human to do a machine's job.

  • Paper2ppt

    wp-a/paper2ppt Skill

    4★

    将学术论文转为可编辑、可溯源的中文 PPTX，兼容 Codex 与 Claude Code。

  • Arxiv watcher

    frankaging/lite-research-agents/skills/arxiv-watcher Skill

    3★ repo

    Lite research agents on proposal, experiment and review

  • Arxiv mcp server

    cyanheads/arxiv-mcp-server/io.github.cyanheads/arxiv-mcp-server MCP server

    3★ repo

    Search arXiv, fetch paper metadata, and read full-text content.

  • Literaturverzeichnispruefung

    benedikt-e/literaturverzeichnispruefung Skill

    2★

    Agentic Skill to verify (manly german) academic references and bibliographies for citation errors and AI hallucinations using live database APIs (OpenAlex, K10plus, lobid, DNB, Crossref, Semantic Scholar, ZBW EconBiz, Open Library, arXiv, Library of Congress, GESIS).

  • Arxiv search

    arch3rPro/ark-space/plugins/ark-space/skills/arxiv-search Skill

    2★ repo

    ArkSpace is a creative workspace for orchestrating agent skills, roles, and workflows across Claude Code and Code

  • Arxiv watcher

    Daisybastioned440/lite-research-agents/skills/arxiv-watcher Skill

    2★ repo

    Coordinate agent brainstorming to generate research proposals and manage future experiment and review workflows

  • Format thesis docx

    h46373824-tech/format-thesis-docx-skill/format-thesis-docx Skill

    2★ repo

    Codex skill + Microsoft Word Add-in for AI-assisted thesis DOCX formatting: templates, cover metadata, page numbering, confirmations, and dynamic TOC.

  • Arxiv

    skill-commons/skill-commons/skills/arxiv Skill

    2★ repo

    Git-first hub for open, reusable research Agent Skills

  • Academic researcher

    rakibulism/agent-skills-os/skills/academic-researcher Skill

    2★ repo

    THE UNIVERSAL AGENT SKILLS LIBRARY

  • Scholarly

    ShiyangZheng/scholarly Skill

    no license2★

    An AI agent skill that guides you through writing academic papers and theses, section by section.

  • Academic paper review

    kimtth/agent-skill-100-lines-or-less/skills/academic-paper-review Skill

    no license2★ repo

    🧿 Minimal but effective AI agent skill definitions in 100 lines or less.

  • Ai writing guardrails

    coastlight-ai/ai-writing-guardrails/skills/ai-writing-guardrails Skill

    1★ repo

    Catches the ways AI quietly degrades academic writing: literature bias, confirmation bias, language flattening, hallucinated citations. A Claude skill that enforces phase-gated workflows, decision logging, and session transcripts so the process stays honest.

  • Academic essay

    SkillMedev/academic-researcher/skills/academic-essay Skill

    1★ repo

    Literature reviews, systematic reviews, citations, and policy briefs.

  • Deep research

    B143KC47/deep-research-skill/deep-research Skill

    1★ repo

    Evidence-first deep research skills for AI agents, with source tracking, citations, contradiction checks, and uncertainty-aware synthesis.

  • Phd paper supervisor

    avikbal-dm/phd-paper-supervisor/phd-paper-supervisor Skill

    1★ repo

    A Claude Agent Skill that takes a research paper from idea to a published, citable preprint. Evidence grading, mechanism-first reasoning, and a DOI-to-distribution workflow.

  • Medical research thesis supervisor

    mohamedhadyashry/medical-research-thesis-supervisor/medical-research-thesis-supervisor Skill

    1★ repo

    A Claude Agent Skill that turns Claude into a rigorous medical research supervisor — search strategy, evidence synthesis, scientific writing, and peer-review-grade QA. Never fabricates citations.

  • Pdflatex skill

    b1rd33/pdflatex-skill Skill

    1★

    Lean LaTeX skill for Claude Code — 6 templates, 9 references, ~2K token context cost, zero Python dependencies. Invoices, reports, CVs, presentations, academic papers.

  • Finance literature review

    azazhang/finance-literature-review-skill/.cursor/skills/finance-literature-review Skill

    1★ repo

    Finance-first literature review skill pack for Codex, Cursor, Claude, Gemini, and Copilot.

  • Thesis

    VictorAurelius/claude-starter-kit/skills/document-generation/thesis Skill

    1★ repo

    🤖 Battle-tested Claude Code skills, rules & workflow templates — extracted from a real 200+ PR project. Governance-first. Bilingual VN/EN.

  • Horizontal thesis packaging

    songyijie971-byte/horizontal-thesis-packaging Skill

    1★

    把横向项目、企业系统、AI/RAG/机器人项目转成硕士论文主线的 Agent Skill

  • Arxiv monitor

    Moonweave-Research/groundcheck/arxiv-monitor Skill

    1★ repo

    Verification skills for academic research — grounds every claim in fetched evidence, not memory. Citation/figure/contradiction checking, arXiv monitoring, NRF grant writing.

  • Easyreading academic paper

    szddddddd/easyreading-academic-paper/easyreading-academic-paper Skill

    1★ repo

    面向 Codex、Claude Code、Gemini CLI 与 Grok Build 的完整中文学术论文解析 Agent Skill

  • Develop academic paper

    ylzjpky/vibe-academic-writing/plugins/vibe-academic-writing/skills/develop-academic-paper Skill

    1★ repo

    An Agent Skill for academic research, course synchronization, citation auditing, and source-grounded writing.

  • Thesis theory evaluator

    mcmespinaa/thesis-theory-evaluator Skill

    0★

    Claude Code skill that evaluates a thesis Theoretical Framework chapter against the OL646E (Malmö University SALSU) course rubric. Companion to thesis-anchoring-map.

  • Cat paper search

    jy1529098645-gif/Cat_paper_search Skill

    0★

    🔍 Find real academic papers across 5 scholarly databases & deep-read any open-access PDF — grounded, never fabricated. Runs on Claude, ChatGPT & DeepSeek. A lite, open-source edition of AcademiCats. 跨 5 大学术库检索真实论文、精读 PDF —— 可在 Claude / ChatGPT / DeepSeek 上使用。

  • Arxiv prep

    SeidSmatti/misc-CC-Plugins/plugins/academic-latex/skills/arxiv-prep Skill

    0★ repo

    Personal multi usage Claude Code plugins/skills marketplace

  • Cat paper review

    jy1529098645-gif/Cat_paper_review Skill

    0★

    🧪 Peer-review your draft across 5 lenses, methodology checked against the right standard per paper type (STROBE/PRISMA/CONSORT/COREQ/Toulmin). Referee letter + scored verdict. Runs on Claude, ChatGPT & DeepSeek. A lite, open-source edition of AcademiCats. 按论文类型套用学术标准的模拟同行评审 —— 可在 Claude / ChatGPT / DeepSeek 上使用。

  • Grounded research

    ahoyvarun/grounded-research/grounded-research Skill

    0★ repo

    A Claude Skill that verifies research writing - catches fabricted citations, unsupported claims and hidden contradictions

  • Literature review

    kenantang/codex-and-claude-skills/collected-academic-research-skills/sources/AI-4-Phi__PhilLit/.claude/skills/literature-review Skill

    no license0★ repo

    Generated by Codex. Read with caution.

  • Startup thesis builder

    apswin/startup-idea-evaluator/startup-thesis-builder Skill

    0★ repo

    A Claude skill that turns a startup idea into a VC-ready strategy doc and pitch deck. Describe the idea in a sentence; it researches, stress-tests the thesis, and writes the documents.

  • Scholar sidekick api

    mlava/scholar-sidekick-skills/skills/scholar-sidekick-api Skill

    0★ repo

    Installable Agent Skills for Scholar Sidekick — turn DOI/PMID/ISBN/arXiv/ISSN/ADS/WHO IRIS into citations (10,000+ CSL styles), exports (BibTeX/RIS/EndNote/CSV), and retraction / open-access / fabrication checks. Zero-install REST skill + MCP skill.

All 619 in the catalog